Skip to content

WS-DINO: a novel framework to use weak label information in a self-supervised setting to learn phenotypic representations from high-content fluorescent images of cells.

crosszamirski/WS-DINO

Repository files navigation

WS-DINO

Pytorch implementation of Self-Supervised Learning of Phenotypic Representations from Cell Images with Weak Labels

UPDATE

This paper has been accepted to LMRL @ NeurIPS 2022. We look forward to presenting in December.

Citation

If you find this work useful, please consider citing our paper:

@article {10.48550/arXiv.2209.07819,
	author = {Cross-Zamirski, Jan and Mouchet, Elizabeth and Williams, Guy and Sch{\"o}nlieb, Carola-Bibiane and Turkki, Riku and Wang, Yinhai},
	title = {Self-Supervised Learning of Phenotypic Representations from Cell Images with Weak Labels},
	year = {2022},
	doi = {https://doi.org/10.48550/arXiv.2209.07819},
	journal = {arXiv Preprint arXiv:2209.07819}
}

About

WS-DINO: a novel framework to use weak label information in a self-supervised setting to learn phenotypic representations from high-content fluorescent images of cells.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages